© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101863
    Prev
    Next
    INDEX
    Explanations

    metadata-related terms and elements associated with academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pokrač
    -0.47
     subsequently
    -0.44
    ⦁
    -0.43
    empêcher
    -0.43
    extAlignment
    -0.43
    #
    -0.42
    aneously
    -0.42
    accompag
    -0.42
    IsContent
    -0.41
    ITUD
    -0.41
    POSITIVE LOGITS
     lenker
    0.78
     disambiguazione
    0.58
     nahilalakip
    0.52
     חיצוניים
    0.50
    UseVisualStyle
    0.49
    QMetaType
    0.48
    adaptiveStyles
    0.48
     Exacts
    0.47
    rungsseite
    0.47
    setObjectName
    0.47
    Activations Density 0.002%

    No Known Activations